Claim Missing Document
Check
Articles

IMPLEMENTASI METODE SCRUM PADA PERANCANGAN SISTEM INFORMASI TATA USAHA SEKOLAH BERBASIS WEB Mardika, Putri Dina; Ahmad Fauzi; Nilma
Jurnal Publikasi Teknik Informatika Vol. 1 No. 1 (2022): Januari : Jurnal Publikasi Teknik Informatika
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jupti.v1i1.188

Abstract

The use of information technology which is increasingly becoming an important need for all sectors of people's lives with all the conveniences offered such as speed and good data processing accuracy makes this difficult for today's society to do. In the world of education, information technology is also used in data processing in the administrative section. MTs Sirojul Athfal which still uses conventional methods, needs an information system to process student payment data so as to reduce errors in data processing. The Scrum method is very well used in the process of making information systems that require fast time to implement. The purpose of this research is to implement the SCRUM method in the design of the MTs Administrative Information System. The results of this study indicate that the SCRUM method is very well used in the manufacture of Information Systems, which requires fast time and needs dynamic information systems in the process.
Evaluasi Kinerja Algoritma Naïve Bayes untuk Diagnosis Kanker Paru Berbasis Data Klinis Terstruktur Nunu Kustian; Putri Dina Mardika; Reko Syarif Hidayatullah
Jurnal Informatika Dan Tekonologi Komputer (JITEK) Vol. 6 No. 2 (2026): Juli : Jurnal Informatika dan Tekonologi Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jitek.v6i2.11077

Abstract

The rising incidence of lung cancer is often outpaced by the constraints of medical resources, creating a critical gap that frequently leads to diagnostic delays and hindered treatment interventions. Early-stage detection is therefore fundamentally important to boost therapy efficacy and extend patient survival rates. This study proposes a computational diagnostic model utilizing the Naïve Bayes algorithm to classify lung cancer status based on structured clinical datasets encompassing demographic profiles, smoking behaviors, and patient reported symptoms. Data integrity was prioritized through rigorous preprocessing, which included handling missing values and transforming categorical variables into a numerical format suitable for probabilistic modeling. The Naïve Bayes framework was chosen for its interpretability, robustness, and efficiency in handling tabular clinical data. Empirical evaluations yielded highly promising results, with the proposed model achieving an accuracy of 95%, precision of 98%, recall of 96%, and an F1-score of 97%. These findings validate the capability of the algorithm to provide dependable diagnostic predictions, demonstrating its potential as a decision support tool to streamline early screening processes for lung cancer.